JP6144408B2 - Energy measurement information labeling system and energy measurement information labeling server - Google Patents

Description

  The present invention relates to an energy measuring device that measures energy usage information for individual energy devices or parts with respect to energy devices connected to a power draw-in point, and a system that labels the measured information.

  Conventional energy monitoring devices using AMI, AMR, and digital watt-hour meters measure only total power usage information generated by combining individual energy devices. Therefore, in order to extract the energy usage information of individual energy devices, it is necessary to install a large number of individual energy measuring devices or install an energy measuring device using a large number of sensors in the distribution board. It was. However, when a measuring device is installed for each individual energy device, there arises a problem that the installation space is restricted and the capital investment increases. Furthermore, even when a large number of sensors in the distribution board are used, there is a limit in obtaining energy usage information for individual energy devices as well as an increase in capital investment due to the adoption of a large number of sensors.

  In order to solve this problem, various researches have been conducted to efficiently extract the energy usage information of individual energy devices from the power draw-in point. Of these, a typical method is to simply measure signal information such as current, voltage, power, etc. with an energy measuring device, then send it directly to a specific server, and extract the energy usage information of individual energy devices through a series of computer operations. is there. However, in order for such a technology to reach the regular use stage, it is extremely important to develop an energy measuring device capable of performing prior signal information processing so that processing / storage / management for large-capacity data of a server becomes flexible. . Prior signal information processing is related to signal information sampling and clustering of a specific data set (for example, data corresponding to the same energy device). The information processed at this time must maintain a level of resolution that can be divided into individual energy devices or parts during the computation of the server computer.

  In the present invention, a specific point (mainly a power drawing point of a switchboard or distribution board) where a number of energy devices that use electrical energy in a single building or home and parts in the device (hereinafter referred to as load devices) are combined. We propose an energy measurement device that measures energy usage information using only a single sensor such as a Hall sensor.

  After transmitting the energy usage information measured in this way to the server, the server estimates and labels the energy usage information of the individual load devices through a series of computer operations, and then transmits analysis information on these to the user. The purpose is to propose a system that can provide consulting related to energy use.

  In order to solve the technical problems as described above, the power draw-point energy measuring device according to the present embodiment is configured such that the voltage, current, active power, or invalidity from at least one power draw point and a single sensor to a plurality of load devices. A power information collecting unit that collects power information including a power signal, and an operating state for extracting an operating state of the individual load device or a change pattern of the operating state by classifying a normal or excessive state due to a change in voltage or power signal from the power information An extraction unit; and a data set generation unit that generates a data set for each individual load device that is matched with the operation state or the change pattern of the operation state based on a signal correlation according to characteristics of power use of the individual load device.

  Preferably, the power information collecting unit collects a voltage or current snapshot of an AC waveform having a period predetermined by the power information.

  The operation state extraction unit may classify the snapshots according to the extracted operation state or a change pattern of the operation state.

  The signal correlation includes at least one of voltage / current correlation, high-frequency distortion, current / power snapshot signal deformation, and active / reactive power correlation as power usage characteristics of the load device.

  The data generation unit preferably generates a data set corresponding to each load device, that is, the same energy device or the same component.

  The power pull-in point energy measurement device further includes a transmission unit that recombines the data sets and transmits the generated data set to a labeling server that generates labeled power information.

  In order to solve the technical problem, the labeling server according to the present embodiment includes a receiving unit that receives a data set generated by classifying power information based on an individual load device, and an individual load for the received data set. A recombination unit that reclassifies the parts according to the operation characteristics of the device, maps them according to the time domain, and recombines them, and a labeling unit that labels the recombined data sets.

  The recombination unit may map the reclassified data set to a time-domain power usage trend, sort the data sets by parts of the individual load equipment, and recombine the parts according to the same load equipment characteristics. preferable.

  It is preferable that the labeling server determines a state of the individual load device by sensing a change in the data set based on a result of the division by the data set for each component of the individual load device.

  In order to solve the technical problem, the power draw point energy measurement information label system according to the present embodiment includes power including voltage, current, active power, or reactive power signal at at least one power draw point for a plurality of load devices. An operation state extraction unit that collects information and extracts an operation state of the individual load device or a change pattern of the operation state by classifying a normal or excessive state due to a change in voltage or power signal from the power information, and the power of the individual load device A power pull-in point energy measuring device that generates and transmits a data set for each individual load device that is matched with an operation state of the load device or a change pattern of the operation state based on a signal correlation depending on usage characteristics, and receiving the data set Reclassify by parts according to the operating characteristics of the individual load devices and map by time domain Recombined Te, it includes a power information labeling server to label the recombined data set.

  According to the present invention, it is possible to expand an infrastructure that provides users with an active energy saving solution based on energy use information measurement for individual load devices using an energy measurement device capable of performing prior information processing.

  In other words, the combination of the energy measurement device that executes the hardware algorithm and the server that executes the software algorithm so that pre-processing can be performed prevents excessive time delay due to the execution of a series of operations and reduces traffic related to information communication. Can do. As a result, there is no burden of constructing an expensive system by installing a large number of individual energy equipment monitoring devices or branch circuit measuring devices, and the rapid expansion and realization of a non-intrusive load monitoring energy saving market. Is possible.

It is the block diagram which showed the power drawing-in point energy measuring device by one Embodiment of this invention. It is the flowchart which showed operation | movement of each structure of the power drawing-in point energy measuring device by one Embodiment of this invention. It is the flowchart which showed operation | movement of each structure of the power drawing-in point energy measuring device by one Embodiment of this invention. It is the flowchart which showed operation | movement of each structure of the power drawing-in point energy measuring device by one Embodiment of this invention. 1 is a block diagram illustrating a labeling server according to an embodiment of the present invention. 5 is a flowchart illustrating an operation of a labeling server according to an exemplary embodiment of the present invention.

  The following is merely illustrative of the principles of the invention. As such, those skilled in the art can implement the principles of the invention and invent various devices that fall within the concept and scope of the invention, although not explicitly described or illustrated herein. Moreover, all conditional terms and embodiments listed herein are in principle and are expressly intended only for the purpose of allowing the concepts of the invention to be understood, and as such It should be understood that the invention is not limited to the embodiments and conditions listed in.

The above objects, features and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, by which those skilled in the art to which the invention pertains shall have the technical idea of the invention. Could be easily implemented.
In describing the invention, if it is determined that a specific description of a known technique related to the invention may unnecessarily obscure the gist of the invention, a detailed description thereof will be omitted. Hereinafter, description will be given with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing a power draw point energy measuring apparatus 100 according to an embodiment of the present invention.

  In the present embodiment, the power pull-in point energy measuring apparatus 100 is an unnamed load clustering data set for estimating the energy usage of individual energy devices and internal components connected to the pull-in point in the total power consumption energy at the power pull-in point. Is executed, and is transmitted to the specific server 200.

  That is, the power drawing point energy measuring device 100 according to the present embodiment is installed together with a single sensor at the power drawing point, and can measure a total electric energy usage amount and estimate the energy usage amount of an individual load device. It is a device equipped with a hardware algorithm. The prior information processing process for each load device executed by the hardware algorithm is summarized as follows.

  First, a snapshot is extracted from the voltage / current signal, a reference point is extracted, noise filtering is performed, and normal / transient states such as voltage, active power, reactive power, etc. are classified based on the corresponding results. To extract the operating state and the operating state change such as the on / off event of the individual load device. Then, the final clustering data set is generated as the pattern matching load classification based on the voltage-current correlation degree, the high frequency distortion degree, the current / power snapshot signal deformation degree, the active / reactive power correlation degree, and the like related to the load feature. The generated clustering data set is compressed with an anonymous name that cannot be recognized by the user (for example, load classification mark such as 1, 2, 3 or A, B, C, etc.) and sent to a specific server or cloud Is done.

  Hereinafter, it will be described in more detail with reference to FIG. Referring to FIG. 1, the power pull-in point energy measuring apparatus 100 according to the present embodiment includes a power information collection unit 110, an operation state extraction unit 120, a data set generation unit 130, and a transmission unit 140.

  The power information collection unit 110 according to the present embodiment collects power information including a power signal at at least one power pull-in point for a plurality of load devices.

  The load equipment includes energy use equipment or parts that use electrical energy. The power draw-in point is a point (node) where power is drawn into a plurality of load devices, such as the power draw-in point of each household switchboard or distribution board. Hereinafter, the operation of the power information collection unit 110 according to the present embodiment will be described in more detail with reference to FIG.

  In the present embodiment, the power information collection unit 110 first executes a power signal measurement step S112. The power signal measurement step S112 measures an unprocessed power information waveform of current and voltage using an energy measuring device and a single sensor installed at a power draw point.

  Next, the power information collection unit 110 executes a snapshot extraction step S114. The snapshot extraction step S114 collects a voltage or current snapshot of an AC waveform having a predetermined period. In the present embodiment, it is preferable to extract a voltage having a periodic waveform of alternating current and a high-frequency current snapshot.

  Next, the operation state extraction unit 120 according to the present embodiment classifies the normal or excessive state of the power change from the collected voltage or power information, and extracts a change pattern of the operation state or the operation state of the load device. This will be described in more detail with reference to FIG.

  Referring to FIG. 3, the operation state extraction unit 120 first executes power information and reference point extraction step S116. That is, real-time power usage and power quality information are extracted, and a reference point for normal or excessive state classification is extracted.

  In the present embodiment, the reference point is a power usage amount that is constantly used without being fluctuated while being always on without being turned on / off by an individual load device by extraction of real-time power usage amount and power quality information. It is preferable.

  Next, the excessive response separation step S118 extracts an excessive state section in which the power usage is turned on / off or the operation state is changed by the operation of the individual load device.

  Furthermore, in this embodiment, the operation state extraction unit 120 can execute the noise removal step S120. The noise removing step S120 removes a meaningless high frequency noise signal generated in the power signal measurement of the total power usage.

  Further, the operation state extraction unit 120 classifies the snapshots according to the extracted operation state or a change pattern of the operation state. For example, in the case of a snapshot that is determined to be an excessive response operation, the snapshot extraction frequency may be much higher than in a normal state.

  Referring to FIG. 3 again, before clustering by individual load device in the on / off event detection step S122, snapshots for events and the like are classified according to their on / off states.

  Next, the state transition change detection step S124 detects and classifies a change pattern of the operation state with respect to a load having a multi-step other than the on / off operation or having a continuous change characteristic.

  After detecting the state transition change, the real-time total power consumption data processing step S126 generates power information data calculation, storage, and transmission data packages for the total energy usage and power quality information for the real-time power usage service.

  Next, the data set generation unit 130 according to the present embodiment generates a data set for each individual load device that is matched with the operation state or the change pattern of the operation state based on the signal correlation according to the power usage characteristics of the individual load device. . Hereinafter, it will be described in more detail with reference to FIG.

  Referring to FIG. 4, the data set generation unit 130 performs a load feature extraction step S130.

  In the present embodiment, the load feature extraction step S130 reflects the power usage characteristics of the individual load devices by using the snapshot, transient response, on / off event, and state transition change information extracted from the total power usage data. Generate a signal correlation. The signal correlation may include voltage / current correlation, high frequency distortion, current / power signal deformation, active / reactive power correlation, and the like.

  Next, the data set generation unit 130 performs on / off event matching and pattern matching load classification for generating the data set.

  That is, the on / off event matching step S132 classifies on / off operation events for individual devices into pairs of the same device based on the generated signal correlation, and the pattern matching load classification step S134 generates the generated signal correlation. Based on the relationship, multi-stage or continuous change characteristics for the same device are classified as a linkage group with on / off action events.

  Next, the data set generation step S136 generates a data set grouped as a cooperation group by on / off event matching and pattern matching load classification.

  When the data set is generated, the transmission unit 140 combines the data sets again, and transmits the generated data set to the labeling server 200 that generates the labeled power information.

  Prior to the transmission, in the present embodiment, the generated data package made by the energy measuring device can be compressed so that a large amount of data can be easily transmitted to a specific server.

  It is also possible to transmit both power consumption and quality information data necessary for executing the real-time power energy information service.

  Hereinafter, a labeling server 200 that receives the data set generated by the power pull-in point energy measuring apparatus 100 according to the above-described embodiment and generates labeled power information will be described with reference to FIG.

  The labeling server 200 according to the present embodiment uses the power usage at the power pull-in point through processes such as machine learning and automatic labeling based on the transmitted clustering data set by load, real-time power usage, and power quality information data set. Consultation on energy usage information and energy-saving tips can be executed. That is, it can be said that the labeling server is a large-capacity data processing procedure that displays the total energy information transmitted from the energy measuring device and the energy information for each individual load device to enable various energy saving solutions and consulting. .

  That is, the labeling server 200 according to the present embodiment executes a specific post-processing information process by a software algorithm. The process reclassifies the anonymous load clustering data set into a multidimensional plane with reference areas such as active power, reactive power, time, etc., and sets the classification boundary surface in the same load device by machine learning to turn on / off, It is classified by specific operation or parts such as multi-stage, continuous change, and continuous maneuver.

  After mapping this to the real-time power consumption transition in the time domain and completing the classification, grouping (1 + 2 + 3 or A + B + C, etc.) with the same device that allows the user to recognize the subordinate parts of the individual load device, saved Automatic labeling is performed by matching with naming data sets of individual load devices (refrigerators, washing machines, air conditioners, etc.).

  At this time, an energy device that has not been automatically labeled with data that is not in the named data set is manually labeled by means such as manually turning on / off the device and checking the corresponding time. The manually generated data is then added back to the collected data set for future automatic labeling.

  Hereinafter, it will be described in more detail with reference to FIG.

  Referring to FIG. 5, the labeling server 200 according to the present embodiment includes a receiving unit 210, a recombination unit 220, and a labeling unit 230.

  First, the receiving unit 210 classifies the power information based on the component units constituting the individual load device, and receives the generated data set.

  Next, the recombination unit 220 reclassifies the received data set into a multi-dimensional plane according to the operation characteristics of the individual load device, and maps and recombines them according to the time domain.

  Prior to this, the recombination unit 220 can execute the data decompression step S202 first. That is, when the power pull-in point energy measuring apparatus 100 transmits compressed data, the data compression can be released in order to increase the execution speed of the software algorithm.

  When the compression is released, the recombination unit 220 maps the reclassified data to the power consumption amount transition in the time domain and recombines the components in the same load device. This will be described in more detail with reference to FIG.

  FIG. 6 is a flowchart illustrating the steps executed by the recombination unit 220 according to an embodiment of the present invention.

  Referring to FIG. 6, in the large classification load device classification step S204, the distribution plane is divided according to the load operation characteristics (on / off, multi-step, continuous change, constant mobility) for the individual load devices determined to be the same device.

  Next, the feature-specific clustering step S206 reconstructs a multidimensional plane so that the distribution plane boundary can be easily set by linking the clustering data set and the large classification load device classification. In order to reconstruct the multidimensional plane, active power, reactive power, time, and the like can be used as reference regions.

  When the multi-dimensional plane is reconstructed, the machine learning step S208 uses a clustering result for each energy device and a state learning algorithm-based machine learning method such as an artificial intelligence network to perform operations of individual load devices or between components. Generate boundary classification criteria. The specific load device classification boundary setting step S210 reclassifies the data by executing the individual component level load classification for the clustering data using the classification criterion of the machine learning boundary. At this time, the detailed load classification of the bearer system is determined from the total power amount to the component level for the individual energy equipment.

  Next, the time domain mapping step S212 maps the data set for the anonymous part reclassified in the process to the real time data in the time domain.

  In the classification step S214, the mapped data is classified according to a part level according to various colors or display methods recognizable by a user.

  Next, in the same load recombination stage S216, the lower parts in the individual load equipment generated in the classification stage are combined to generate a group as a load equipment that can be recognized by the user. As an example, the compressor, motor, lamp, control circuit characteristics, etc. generated in the division stage are combined and grouped in a refrigerator (internal numbers such as 1, 2, 3 and unnamed temporary marks such as A, B, C etc.) use).

  After execution of the recombination phase, the labeling unit 230 labels the combined data set again. For example, the name of the corresponding load device is automatically matched with the saved load device data set for the anonymous temporary mark data classified as the individual load device. As an example, A, B, C, etc. can be automatically named on a refrigerator, TV, washing machine, etc., by a matching algorithm with a data pattern and stored data.

  In this embodiment, the labeling can be manually input. For a load that does not match the saved load device data and exists without a mark even though automatic labeling has been executed, the developer or user manually names the device and inputs it. A method using the on / off time of the device is also possible.

  In addition, for individual load devices for which manual labeling has been performed, the corresponding load device data set can be expanded by naming the corresponding data and storing it separately.

  Note that the labeling server 200 can provide data interpretation information using individual load device energy usage information. That is, it is also possible to generate a specific data set by applying data interpretation based on a behavioral psychology analysis algorithm to the total power and individual load equipment energy usage patterns.

  Also, it is possible to automatically generate an expert consulting chip that can guide the user's energy saving by the data interpretation.

  In addition, an integrated service that provides the total power amount, individual load device usage amount, energy saving consulting, etc. to a specific building and unit home by an energy IT specialist is also possible.

  Among various energy consulting, as an example, the user senses the change of the clustering data set distinguished by the component level in relation to the state of the individual load device and judges the component aging state and failure state of the individual load device and uses it Can also be provided.

  According to the above embodiment, by extracting and executing the hardware algorithm of the measuring instrument and the software algorithm of the server for the total power usage information at the power draw-in point, the component individual energy usage information of various load devices is extracted. Can do.

  In addition, because the software algorithm of the server is flexibly combined with a single energy measuring device, there is no high-cost burden of installing a system with a large number of devices. Energy saving methods can be derived. In particular, energy usage information above the branch circuit level can be acquired without adopting a large number of sensors in the distribution board.

  In summary, in the present invention, in extracting individual load equipment energy usage information from the total electrical energy usage information measured at the power draw-in point, the specific server does not execute the overall algorithm, but the energy measuring equipment (prior Information processing processor, hardware algorithm, clustering data set generation, etc.) and server (post-processing information processor, software algorithm, labeling and energy saving hint generation, etc.) are executed in a binary manner. In other words, the pre-information processing is executed so that the single energy measuring device has a resolution capable of distinguishing between the components, and the server emphasizes the data storage and pattern interpretation and data utilization, which are its advantages, Flexibility can be ensured in the processing / storage / management of large volumes of data related to the energy usage of various loads.

  The above description is merely illustrative of the technical idea of the present invention, and a person having ordinary knowledge in the technical field to which the present invention belongs can be used without departing from the essential characteristics of the present invention. Various modifications, changes, and substitutions may be possible.

  Accordingly, the embodiments disclosed in the present invention and the accompanying drawings are for the purpose of explaining, not limiting, the technical idea of the present invention, and the technical idea of the present invention is described based on such an embodiment and the accompanying drawings. The scope of this should not be limited. The protection scope of the present invention should be construed by the appended claims, and all technical ideas within the equivalent scope should be construed as being included in the scope of the right of the present invention.

Claims (10)

A power information collection unit that collects power information including voltage signals at at least one power pull-in point for a plurality of load devices;
An operation state extraction unit that extracts normal or excessive states of power change from the collected power information and extracts an operation state or a change pattern of the operation state corresponding to the event of the load device, and the operation state extraction unit extracts A data set generation unit for generating a data set indicating the operation state or a change pattern of the operation state;
A power pull-in point energy measuring device having
The data set the data set generation unit has generated, and classified into a multidimensional plane including the active and reactive power, to associate a data set is classified into one in which individual load devices of the plurality of load devices Reunion department, and
A labeling unit that labels the data set associated with the individual load device by the recombination unit ;
A power pull-in point energy measurement information labeling server,
Power entry point energy measurement information labeling system with.   The power drawing point energy measurement information labeling system according to claim 1, wherein the power information collecting unit collects a voltage or current snapshot of an AC waveform having a predetermined period based on the power information.   The power drawing point energy measurement information labeling system according to claim 2, wherein the operation state extraction unit classifies the snapshots according to the extracted operation state or a change pattern of the operation state. The data set generation unit generates the data set according to a signal correlation according to a power usage characteristic of the individual load device, and the signal correlation includes a voltage / current correlation degree, a high frequency as a power usage characteristic of the load device. The power drawing point energy measurement information labeling system according to claim 2, comprising at least one information of distortion, current / power snapshot signal deformation, active / reactive power correlation.   The said data set production | generation part classifies | categorizes the said electric power information based on the component unit which comprises the said individual load apparatus, and produces | generates the said individual load apparatus or a data set classified by components, The Claim 1 characterized by the above-mentioned. Power entry point energy measurement information labeling system.   The apparatus of claim 1, further comprising: a transmitting unit that recombines the data sets and transmits the generated data set to a labeling server that generates labeled power information. Power draw point energy measurement information labeling system described.   The power pull-in point energy measurement information labeling server further includes a recombination unit that maps the classified data sets to a time domain power consumption transition and combines data sets corresponding to components in the same load device. The power pull-in point energy measurement information labeling system according to any one of claims 1 to 6, characterized by comprising:   The power pulling point energy measurement information labeling system according to claim 7, wherein the labeling unit performs labeling in association with the individual load device that is the load device in which the recombination unit combines the data sets. . The operation state corresponding to the event of the load device, which is extracted by classifying the normal or excessive state of the power change from the power information in which the power information including the voltage signal is collected at at least one power pull-in point for a plurality of load devices. Or a receiving unit that receives a data set indicating a change pattern of the operating state ,
The data sets received by the receiving unit, classifying the multidimensional plane including the active and reactive power, re-union that associates a data set is classified into one in which individual load devices of the plurality of load devices And
The power retraction point energy measurement information labeling server , comprising: a labeling unit that labels the data set associated with the individual load device by the recombination unit . The method according to claim 9, further comprising a recombination unit that maps the classified data set to a time domain power consumption transition and combines data sets corresponding to components in the same load device. The power pull-in point energy measurement information labeling server described.

Images